© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 10330
    Prev
    Next
    INDEX
    Explanations

    nl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NL
    -1.61
     NL
    -1.12
    nl
    -1.08
     nl
    -0.84
     merry
    -0.57
     ouverts
    -0.53
     Normdatei
    -0.51
    ghijkl
    -0.50
     giusti
    -0.50
    ryn
    -0.49
    POSITIVE LOGITS
    ADVERTISEMENT
    0.65
     fonder
    0.64
    e
    0.58
    hoga
    0.56
     phấn
    0.55
    ezers
    0.53
     spell
    0.52
    ={({
    0.52
     تضيفلها
    0.52
    DeleteCommand
    0.51
    Activations Density 0.010%

    No Known Activations